© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 46158
    Prev
    Next
    INDEX
    Explanations

    mind followed by common suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     pinned
    -0.13
    inton
    -0.11
    /fast
    -0.11
    hips
    -0.11
    ekt
    -0.11
    bies
    -0.11
    /feed
    -0.11
    /sl
    -0.11
    cee
    -0.11
    enth
    -0.10
    POSITIVE LOGITS
    lessly
    0.19
    sets
    0.17
    /body
    0.15
    less
    0.15
    edly
    0.15
    fulness
    0.14
    ,body
    0.12
    -body
    0.12
    lessness
    0.12
    storms
    0.12
    Activations Density 0.037%

    No Known Activations